Academic management

University of Oviedo

Uniovi.es | Home | Search | Site Map

| |

Bachelor´s Degree in Informatics Engineering in Information Technology
GIITIN01-3-009
Intelligent Systems
General description and schedule Teaching Guide

Coordinator/s:

ANTONIO BAHAMONDE RIONDA
abahamondeuniovi.es

Faculty:

Beatriz Remeseiro Lopez
bremeseirouniovi.es
(English Group)
ANTONIO BAHAMONDE RIONDA
abahamondeuniovi.es
(English Group)
Pablo Pérez Núñez
pabloperezuniovi.es

Contextualization:

The subject of Intelligent Systems (IS) is part of the Intelligent Applications topic of the Application Software module, along with other two subjects: Business Intelligence (BI) and Ambient Intelligence (AMI). The subject is taught in the second semester of the third year (S6). The main contents of the subjects are the basic principles of intelligent systems, in particular the knowledge representation models and the reasoning and learning mechanisms of this type of systems. Thus, the subject is fundamental for the other two subjects related to Intelligent Applications (BI and AMI), and other subjects of the curriculum related to programming and computability theory, in particular Algorithmics and Computability are fundamental to be able to tackle this subject successfully.

 

Requirements:

In order take advantage of this subject, it is recommended that the student takes the Programming subjects first, in particular Algorithmics and Computability, which are taught in previous semesters.

 

Competences and learning results:

It is expected that through this subject the student will acquire the following competences of the Degree in IT Engineering

General competences: GTR1, GTR2, GTR3, GTR4, GTR5, GTR6, GTR7, GTR8.

Specific competences: ECR15 Knowledge and application of the fundamental principles and basic techniques of intelligent systems and their practical application.

 

COMPETENCE

LEARNING RESULT

ECR15

AI1

Know the fundamentals and application fields of the intelligent systems

ECR15

AI2

Use programming tools for intelligent systems

ECR15

AI3

Know the main heuristic search algorithms in state spaces and know how to apply them to solve complex problems

ECR15

AI4

Know and apply other metaheuristics such as evolutionary algorithms to solve problems

ECR15

AI5

Distinguish the main methods of knowledge representation in artificial intelligence and know how to model the knowledge of problems with the fastest method

ECR15

AI6

Know and apply the different inference algorithms associated with

the different models of knowledge representation

ECR15

AI7

Know the fundamental methods of knowledge representation and reasoning under uncertainty

ECR15

AI8

Know some specific methods for problem solving such as

planning, perception or language processing

ECR15

AI9

Know the fundamentals of machine learning and its scope

 

Contents:

  1. Objectives and applications of Artificial Intelligence
  2. Search algorithms
  3. Knowledge representation
  4. Machine learning
  5. Deep learning
  6. Discussion on advanced topics

Methodology and work plan:

The subject requires a total of 150 hours between classroom and non-classroom work of the student organized as follows:

 

  1. Classroom (60 hours)
    1. Theory sessions (28 hours)
    2. Classroom practical sessions / seminars / workshops (7 hours)
    3. IT laboratory sessions (21 hours)
    4. Group tutor sessions (2 hours)
    5. Evaluation sessions (2 hours)
  2. Non-classroom (90 hours)
    1. Autonomous work (60 hours)
    2. Group work (30 hours)

 

 

 

The model proposed for the organization of the teaching activity of the subject and the personal work of the students is summarized in the following tables:

 

 

IN-CLASS WORK

HOMEWORK

Topics

Total hours

Theory sessions

Classroom practical sessions / seminars / workshops

Laboratory practical sessions / fieldwork / IT classes language

Hospital work experience

Group tutor sessions

External practice sessions

Evaluation sessions

Total

Group work

Individual work

Total

Objectives and applications of Artificial Intelligence

4

2

 

 

 

 

 

 

2

 

2

2

Search algorithms

38

4

 

3

 

1

 

 

8

30

 

30

Knowledge representation

13

4

 

4

 

 

 

 

8

 

5

5

Machine learning

13

4

2

4

 

 

 

 

10

 

3

3

Deep learning

51

10

 

10

 

1

 

 

21

 

30

30

Discussion on advanced topics

14

4

5

 

 

 

 

 

9

 

5

5

Evaluation

17

 

 

 

 

 

 

2

2

 

15

15

Total

150

28

7

21

 

2

 

2

60

30

60

90

 

 

MODALITIES

Hours

%

Totals

Classroom

Theory classes

28

18,7

60 (40%)

Classroom practical sessions / seminars / workshops

7

4,7

Laboratory practical sessions / fieldwork / I.T. classes / language

21

14,0

Hospital work experience

 

 

Group tutor sessions

2

1,3

External practical sessions

 

 

Evaluation sessions

2

1,3

Non-classroom

Group work

30

20,0

90 (60%)

Individual work

60

40,0

 

Total

150

 

 

 

Exceptionally, if sanitary conditions require it, non-classroom teaching activities may be included. In this case, the students will be informed of the changes made.

Assessment of students learning:

Ordinary evaluation: Continuous assessment will be the only type of assessment that will be considered in this evaluation. This assessment will consist of two parts, with the following percentages with respect to the final grade of the subject:

  • Theoretical evaluation: 60%
  • Practical evaluation: 40%

 

The theoretical evaluation will consist of the following parts, with the corresponding weights:

  • Final exam: 70%
  • Presentation: 20%
  • Questionnaires: 10%

 

The practical evaluation will consist of the delivery of a series of tasks carried out in the laboratory sessions. The weight of each delivery will be proportional to the number of sessions that are evaluated through it.

 

It is necessary to achieve a minimum of 4 points out of 10 in each part (theory and practice). When the minimum is not reached in any of the parts and, therefore, the subject is not passed, the student's final grade will be adjusted as the minimum between them.

 

If the weight of the activities not carried out by the student exceeds 50% of the total, the final grade will be "Not Presented".

 

Extraordinary evaluation: The evaluation will consist of a single exam that will give the final grade for the subject. In this exam, theoretical and practical concepts will be evaluated.

 

Differentiated evaluation: The evaluation will consist of a single exam that will give the final grade for the subject. In this exam, theoretical and practical concepts will be evaluated.

 

Exceptionally, if sanitary conditions require it, non-face-to-face assessment methods may be included. In this case, the students will be informed of the changes made.

 

Resources, bibliography and documentation:

The following table includes the bibliographic references used in the subject. In addition, the Virtual Campus platform will be used intensively for the development of the subject. In this platform, the students will have access to other resources such as notes, slides, exercises, sample exams, links of interest, etc. It will also be used to enable tasks through which the students will make their deliveries, to send notices and news, and to make any other complementary documentation available.

 

Bibliography

Title

Author(s)

Publisher/year

Artificial Intelligence: A Modern Approach

Stuart Russell and Peter Norvig

Pearson/2010 (3rd Ed.)

Machine Learning

Tom Mitchell

McGraw-Hill/1997

Machine Learning: A Probabilistic Perspective

Kevin P. Murphy

Mit Press, 2012

Data Mining:

Practical Machine Learning Tools and Techniques

Ian Witten, Eibe Frank, Mark Hall

Morgan Kaufmann, 2011

Deep Learning

I. Goodfellow, Y. Bengio, and A. Courville

MIT Press, 2016

 

 

 

 

 

 

 

 

 

 

 

 

 

Software

  • Matlab
  • Weka
  • Python
  • Keras
  • TensorFlow